Abstract:Abstract: Supercritical steam turbosets are highly complex in their structure and working conditions and prone to rub between static and dynamic parts. Induced by different factors, rubbing faults can be divided into full annular rub and partial rub. Since the time-frequency characteristics are similar to each other, discrimination of two kinds of rub faults are hard to proceed using the traditional spectrum analysis methods. In response to make up for this shortage, an intelligent recognition method based on the EMD-SVD and the SVM is proposed. First, IMFs are collected through EMD. Second, the first-four-order IMFs, which contain the main power of the original signal, are extracted to form the characteristic matrix, and singular value decomposition is applied to obtain a series of eigenvalues. Last, the eigenvalues are inputted to train the SVM in order to classify rub faults. The newly developed intelligent recogonition method is used to analyze both the signals collected from rotor test-bed under full annular rub and partial rub conditions. Results from the experiments show that, classification accuracy of this new-developed method is high, especially for the SVM using radial basis as kernel function, where the classification accuracy is up to 96.0%.
熊 炘 杨世锡 甘春标 周晓峰. 转子全周碰摩与局部碰摩的识别方法研究[J]. , 2012, 31(16): 13-17.
XIONG Xin YANG Shixi GAN Chunbiao ZHOU Xiaofeng. Research on Recognition Method for Rotor System underFull Annular Rub and Partial Rub. , 2012, 31(16): 13-17.